enhance: export the Prometheus metrics over OpenTelemetry (#1248)

Push the runner's Prometheus metrics to the OTLP endpoint next to the job traces, so both land in the same backend.

The `/metrics` registry is converted as the [Prometheus compatibility spec](https://opentelemetry.io/docs/specs/otel/compatibility/prometheus_and_openmetrics/) describes and sent through the existing gRPC-free client, so names stay unchanged and no second metrics stack is linked. Metrics are on by default and pushed every interval and once on shutdown, so ephemeral runners report too.

New standard variables, each `OTEL_EXPORTER_OTLP_*` one with `TRACES` and `METRICS` variants:

- `OTEL_METRICS_EXPORTER`, `none` turns metrics off
- `OTEL_METRIC_EXPORT_INTERVAL`, `OTEL_METRIC_EXPORT_TIMEOUT`
- `OTEL_EXPORTER_OTLP_TIMEOUT`, `OTEL_EXPORTER_OTLP_COMPRESSION`
- `OTEL_EXPORTER_OTLP_CERTIFICATE`, `OTEL_EXPORTER_OTLP_CLIENT_CERTIFICATE`, `OTEL_EXPORTER_OTLP_CLIENT_KEY`

---------

Co-authored-by: silverwind <[email protected]>
Co-authored-by: silverwind <[email protected]>
Co-authored-by: bircni <[email protected]>
Reviewed-on: https://gitea.com/gitea/runner/pulls/1248
Reviewed-by: silverwind <[email protected]>
Reviewed-by: bircni <[email protected]>
Co-authored-by: wmTJc9IK0Q <[email protected]>
This commit is contained in:
authored and bircni committed 2026-10-01 12:55:16 +00:00
1 parent d93b7d278a
commit 568f89d186
7 files changed
+482 -72

No files matched your search

+6 -6
View File
@@ -72,7 +72,7 @@ func runDaemon(ctx context.Context, daemArgs *daemonArgs, configFile *string) fu
defer func() { _ = releaseLock() }()
}
shutdownTelemetry, err := telemetry.Setup(ctx, reg.UUID, reg.Name)
shutdownTelemetry, err := telemetry.Setup(ctx, reg.UUID, reg.Name, metrics.Registry)
if err != nil {
log.WithError(err).Warn("OpenTelemetry export failed to start")
}
@@ -203,12 +203,12 @@ func runDaemon(ctx context.Context, daemArgs *daemonArgs, configFile *string) fu
poller := poll.New(cfg, cli, runner)
metrics.Init() // OTLP exports the registry even without the server
metrics.RunnerInfo.WithLabelValues(ver.Version(), resp.Msg.Runner.Name).Set(1)
metrics.RunnerCapacity.Set(float64(cfg.Runner.Capacity))
metrics.RegisterUptimeFunc(time.Now())
metrics.RegisterRunningJobsFunc(runner.RunningCount, cfg.Runner.Capacity)
if cfg.Metrics.Enabled {
metrics.Init()
metrics.RunnerInfo.WithLabelValues(ver.Version(), resp.Msg.Runner.Name).Set(1)
metrics.RunnerCapacity.Set(float64(cfg.Runner.Capacity))
metrics.RegisterUptimeFunc(time.Now())
metrics.RegisterRunningJobsFunc(runner.RunningCount, cfg.Runner.Capacity)
metrics.StartServer(ctx, cfg.Metrics.Addr, func() (bool, string) {
return poller.Ready(cfg.Metrics.ReadinessGrace)
})